LangChain NY Meetup: How to Evaluate Voice Agents
Join us for an evening in New York with Caroline di Vittorio, the Software Engineer leading the charge on voice agents at LangChain.
Voice agents need to follow the right process, resolve the user’s request, and deliver a conversation that feels fast, clear, and natural.
In this practical session, we’ll show how to evaluate voice agents across three dimensions: execution, outcomes, and experience. You’ll learn how to inspect the full interaction, measure whether the agent achieved its intended goal, and identify voice-specific issues such as latency, interruptions, awkward pauses, and conversational friction.
What You’ll Learn
How to evaluate whether an agent followed its instructions and used tools correctly
How to connect conversations to real-world outcomes such as resolution, booking, or transfer success
How to measure latency, pacing, interruptions, and conversational friction
When to use code evaluators, LLM judges, audio-aware evaluations, and human review
How to trace calls and build a continuous evaluation loop in LangSmith
This meetup is designed for developers and technical teams building voice agents and looking for a more complete way to measure, debug, and improve their performance in production.
Agenda ⏰
6:00 PM: Welcome + Food/Drinks
6:30 PM: Presentation with Caroline (Software Engineer @ LangChain) - How to Evaluate Voice Agents: Execution, outcomes and experience
6:50 PM: Q&A Session with Caroline
7:05 PM: Networking
8:00 PM: Event Ends
Event info:
🎤 Please note this event is fully in-person and will not be live-streamed or recorded.
📍 Location: Address is in Manhattan and will be send out to approved registrants.
🎟️ We can only admit guests with approved registrations. If you’re still on the waitlist or haven’t received a confirmation yet, please stay tuned for future events—but please sit this one out.
About the host:
LangChain enables every company to own their intelligence. LangChain's open, model-agnostic harnesses give teams choice and control over how they build their agent architecture. LangSmith brings testing, deployment, and monitoring together so teams can continuously improve their agents, compound intelligence, and govern them at scale. More than 7,000 customers, including Nvidia, Bridgewater, LinkedIn, Workday, Harvey, and Rippling trust LangSmith to improve their agents across the Agent Development Lifecycle. Learn more: www.langchain.com